library(tidyverse)
## Warning: package 'tidyverse' was built under R version 3.6.3
## -- Attaching packages ------------ tidyverse 1.3.0 --
## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.3 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0
## Warning: package 'ggplot2' was built under R version 3.6.3
## Warning: package 'tibble' was built under R version 3.6.3
## Warning: package 'tidyr' was built under R version 3.6.3
## Warning: package 'purrr' was built under R version 3.6.3
## Warning: package 'dplyr' was built under R version 3.6.3
## -- Conflicts --------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
Confirmed_State_6_13 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/06-13-2020.csv")) %>%
filter (Country_Region == "US") %>%
group_by(Province_State, Country_Region) %>%
summarise(Confirmed = sum(Confirmed))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_datetime(format = ""),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` regrouping output by 'Province_State' (override with `.groups` argument)
str(Confirmed_State_6_13)
## tibble [58 x 3] (S3: grouped_df/tbl_df/tbl/data.frame)
## $ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ Country_Region: chr [1:58] "US" "US" "US" "US" ...
## $ Confirmed : num [1:58] 24601 653 34660 12095 150018 ...
## - attr(*, "groups")= tibble [58 x 2] (S3: tbl_df/tbl/data.frame)
## ..$ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## ..$ .rows : list<int> [1:58]
## .. ..$ : int 1
## .. ..$ : int 2
## .. ..$ : int 3
## .. ..$ : int 4
## .. ..$ : int 5
## .. ..$ : int 6
## .. ..$ : int 7
## .. ..$ : int 8
## .. ..$ : int 9
## .. ..$ : int 10
## .. ..$ : int 11
## .. ..$ : int 12
## .. ..$ : int 13
## .. ..$ : int 14
## .. ..$ : int 15
## .. ..$ : int 16
## .. ..$ : int 17
## .. ..$ : int 18
## .. ..$ : int 19
## .. ..$ : int 20
## .. ..$ : int 21
## .. ..$ : int 22
## .. ..$ : int 23
## .. ..$ : int 24
## .. ..$ : int 25
## .. ..$ : int 26
## .. ..$ : int 27
## .. ..$ : int 28
## .. ..$ : int 29
## .. ..$ : int 30
## .. ..$ : int 31
## .. ..$ : int 32
## .. ..$ : int 33
## .. ..$ : int 34
## .. ..$ : int 35
## .. ..$ : int 36
## .. ..$ : int 37
## .. ..$ : int 38
## .. ..$ : int 39
## .. ..$ : int 40
## .. ..$ : int 41
## .. ..$ : int 42
## .. ..$ : int 43
## .. ..$ : int 44
## .. ..$ : int 45
## .. ..$ : int 46
## .. ..$ : int 47
## .. ..$ : int 48
## .. ..$ : int 49
## .. ..$ : int 50
## .. ..$ : int 51
## .. ..$ : int 52
## .. ..$ : int 53
## .. ..$ : int 54
## .. ..$ : int 55
## .. ..$ : int 56
## .. ..$ : int 57
## .. ..$ : int 58
## .. ..@ ptype: int(0)
## ..- attr(*, ".drop")= logi TRUE
Confirmed_State_9_13 <- read_csv(url("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/09-13-2020.csv")) %>%
filter (Country_Region == "US") %>%
group_by(Province_State, Country_Region) %>%
summarize(Confirmed = sum(Confirmed))
## Parsed with column specification:
## cols(
## FIPS = col_double(),
## Admin2 = col_character(),
## Province_State = col_character(),
## Country_Region = col_character(),
## Last_Update = col_character(),
## Lat = col_double(),
## Long_ = col_double(),
## Confirmed = col_double(),
## Deaths = col_double(),
## Recovered = col_double(),
## Active = col_double(),
## Combined_Key = col_character(),
## Incidence_Rate = col_double(),
## `Case-Fatality_Ratio` = col_double()
## )
## `summarise()` regrouping output by 'Province_State' (override with `.groups` argument)
str(Confirmed_State_9_13)
## tibble [58 x 3] (S3: grouped_df/tbl_df/tbl/data.frame)
## $ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## $ Country_Region: chr [1:58] "US" "US" "US" "US" ...
## $ Confirmed : num [1:58] 138755 6268 208512 70219 761728 ...
## - attr(*, "groups")= tibble [58 x 2] (S3: tbl_df/tbl/data.frame)
## ..$ Province_State: chr [1:58] "Alabama" "Alaska" "Arizona" "Arkansas" ...
## ..$ .rows : list<int> [1:58]
## .. ..$ : int 1
## .. ..$ : int 2
## .. ..$ : int 3
## .. ..$ : int 4
## .. ..$ : int 5
## .. ..$ : int 6
## .. ..$ : int 7
## .. ..$ : int 8
## .. ..$ : int 9
## .. ..$ : int 10
## .. ..$ : int 11
## .. ..$ : int 12
## .. ..$ : int 13
## .. ..$ : int 14
## .. ..$ : int 15
## .. ..$ : int 16
## .. ..$ : int 17
## .. ..$ : int 18
## .. ..$ : int 19
## .. ..$ : int 20
## .. ..$ : int 21
## .. ..$ : int 22
## .. ..$ : int 23
## .. ..$ : int 24
## .. ..$ : int 25
## .. ..$ : int 26
## .. ..$ : int 27
## .. ..$ : int 28
## .. ..$ : int 29
## .. ..$ : int 30
## .. ..$ : int 31
## .. ..$ : int 32
## .. ..$ : int 33
## .. ..$ : int 34
## .. ..$ : int 35
## .. ..$ : int 36
## .. ..$ : int 37
## .. ..$ : int 38
## .. ..$ : int 39
## .. ..$ : int 40
## .. ..$ : int 41
## .. ..$ : int 42
## .. ..$ : int 43
## .. ..$ : int 44
## .. ..$ : int 45
## .. ..$ : int 46
## .. ..$ : int 47
## .. ..$ : int 48
## .. ..$ : int 49
## .. ..$ : int 50
## .. ..$ : int 51
## .. ..$ : int 52
## .. ..$ : int 53
## .. ..$ : int 54
## .. ..$ : int 55
## .. ..$ : int 56
## .. ..$ : int 57
## .. ..$ : int 58
## .. ..@ ptype: int(0)
## ..- attr(*, ".drop")= logi TRUE
setdiff(Confirmed_State_9_13$Province_State, Confirmed_State_6_13$Province_State)
## character(0)
Confirmed_State_9_13 <- Confirmed_State_9_13 %>%
filter(Province_State !="Recovered")
Confirmed_State_6_13_9_13_joined <- full_join(Confirmed_State_6_13,
Confirmed_State_9_13, by = c("Province_State"))
head(Confirmed_State_6_13_9_13_joined)
## # A tibble: 6 x 5
## # Groups: Province_State [6]
## Province_State Country_Region.x Confirmed.x Country_Region.y Confirmed.y
## <chr> <chr> <dbl> <chr> <dbl>
## 1 Alabama US 24601 US 138755
## 2 Alaska US 653 US 6268
## 3 Arizona US 34660 US 208512
## 4 Arkansas US 12095 US 70219
## 5 California US 150018 US 761728
## 6 Colorado US 29002 US 61293
tail(Confirmed_State_6_13_9_13_joined, 5)
## # A tibble: 5 x 5
## # Groups: Province_State [5]
## Province_State Country_Region.x Confirmed.x Country_Region.y Confirmed.y
## <chr> <chr> <dbl> <chr> <dbl>
## 1 Virginia US 53869 US 133742
## 2 Washington US 25538 US 79826
## 3 West Virginia US 2274 US 12705
## 4 Wisconsin US 22518 US 89185
## 5 Wyoming US 1050 US 4346
Confirmed_State_6_13_9_13_joined <- full_join(Confirmed_State_6_13,
Confirmed_State_6_13, by = c("Province_State")) %>%
rename(Confirmed_6_13_2020 = "Confirmed.x", Confirmed_9_13_2020 = "Confirmed.y") %>%
select(-Country_Region.x, -Country_Region.y) %>%
replace_na(list(Confirmed_6_13_2020 = 0))
head(Confirmed_State_6_13_9_13_joined)
## # A tibble: 6 x 3
## # Groups: Province_State [6]
## Province_State Confirmed_6_13_2020 Confirmed_9_13_2020
## <chr> <dbl> <dbl>
## 1 Alabama 24601 24601
## 2 Alaska 653 653
## 3 Arizona 34660 34660
## 4 Arkansas 12095 12095
## 5 California 150018 150018
## 6 Colorado 29002 29002
which(is.na(Confirmed_State_6_13_9_13_joined))
## integer(0)
Confirmed_State_6_13_9_13_joined_long <- Confirmed_State_6_13_9_13_joined %>%
pivot_longer(-c(Province_State),
names_to = "Date", values_to = "Confirmed")
Confirmed_joined_long_plot <- ggplot(Confirmed_State_6_13_9_13_joined_long, aes(x = Confirmed, y = Province_State)) +
geom_col(aes(fill = Date, color = Date))
print(Confirmed_joined_long_plot + ggtitle("Figure 1. Confirmed COVID-19 cases in the US") + labs(y="Province/state", x = "Confirmed cases"))
download.file(url="https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv",
destfile = "data/time_series_covid19_confirmed_global.csv")
time_series_confirmed <- read_csv("data/time_series_covid19_confirmed_global.csv")%>%
rename(Province_State = "Province/State", Country_Region = "Country/Region")
## Parsed with column specification:
## cols(
## .default = col_double(),
## `Province/State` = col_character(),
## `Country/Region` = col_character()
## )
## See spec(...) for full column specifications.
head(time_series_confirmed)
## # A tibble: 6 x 255
## Province_State Country_Region Lat Long `1/22/20` `1/23/20` `1/24/20`
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 0 0 0
## 2 <NA> Albania 41.2 20.2 0 0 0
## 3 <NA> Algeria 28.0 1.66 0 0 0
## 4 <NA> Andorra 42.5 1.52 0 0 0
## 5 <NA> Angola -11.2 17.9 0 0 0
## 6 <NA> Antigua and B~ 17.1 -61.8 0 0 0
## # ... with 248 more variables: `1/25/20` <dbl>, `1/26/20` <dbl>,
## # `1/27/20` <dbl>, `1/28/20` <dbl>, `1/29/20` <dbl>, `1/30/20` <dbl>,
## # `1/31/20` <dbl>, `2/1/20` <dbl>, `2/2/20` <dbl>, `2/3/20` <dbl>,
## # `2/4/20` <dbl>, `2/5/20` <dbl>, `2/6/20` <dbl>, `2/7/20` <dbl>,
## # `2/8/20` <dbl>, `2/9/20` <dbl>, `2/10/20` <dbl>, `2/11/20` <dbl>,
## # `2/12/20` <dbl>, `2/13/20` <dbl>, `2/14/20` <dbl>, `2/15/20` <dbl>,
## # `2/16/20` <dbl>, `2/17/20` <dbl>, `2/18/20` <dbl>, `2/19/20` <dbl>,
## # `2/20/20` <dbl>, `2/21/20` <dbl>, `2/22/20` <dbl>, `2/23/20` <dbl>,
## # `2/24/20` <dbl>, `2/25/20` <dbl>, `2/26/20` <dbl>, `2/27/20` <dbl>,
## # `2/28/20` <dbl>, `2/29/20` <dbl>, `3/1/20` <dbl>, `3/2/20` <dbl>,
## # `3/3/20` <dbl>, `3/4/20` <dbl>, `3/5/20` <dbl>, `3/6/20` <dbl>,
## # `3/7/20` <dbl>, `3/8/20` <dbl>, `3/9/20` <dbl>, `3/10/20` <dbl>,
## # `3/11/20` <dbl>, `3/12/20` <dbl>, `3/13/20` <dbl>, `3/14/20` <dbl>,
## # `3/15/20` <dbl>, `3/16/20` <dbl>, `3/17/20` <dbl>, `3/18/20` <dbl>,
## # `3/19/20` <dbl>, `3/20/20` <dbl>, `3/21/20` <dbl>, `3/22/20` <dbl>,
## # `3/23/20` <dbl>, `3/24/20` <dbl>, `3/25/20` <dbl>, `3/26/20` <dbl>,
## # `3/27/20` <dbl>, `3/28/20` <dbl>, `3/29/20` <dbl>, `3/30/20` <dbl>,
## # `3/31/20` <dbl>, `4/1/20` <dbl>, `4/2/20` <dbl>, `4/3/20` <dbl>,
## # `4/4/20` <dbl>, `4/5/20` <dbl>, `4/6/20` <dbl>, `4/7/20` <dbl>,
## # `4/8/20` <dbl>, `4/9/20` <dbl>, `4/10/20` <dbl>, `4/11/20` <dbl>,
## # `4/12/20` <dbl>, `4/13/20` <dbl>, `4/14/20` <dbl>, `4/15/20` <dbl>,
## # `4/16/20` <dbl>, `4/17/20` <dbl>, `4/18/20` <dbl>, `4/19/20` <dbl>,
## # `4/20/20` <dbl>, `4/21/20` <dbl>, `4/22/20` <dbl>, `4/23/20` <dbl>,
## # `4/24/20` <dbl>, `4/25/20` <dbl>, `4/26/20` <dbl>, `4/27/20` <dbl>,
## # `4/28/20` <dbl>, `4/29/20` <dbl>, `4/30/20` <dbl>, `5/1/20` <dbl>,
## # `5/2/20` <dbl>, `5/3/20` <dbl>, ...
time_series_confirmed_long <- time_series_confirmed %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long),
names_to = "Date", values_to = "Confirmed")
head(time_series_confirmed_long)
## # A tibble: 6 x 6
## Province_State Country_Region Lat Long Date Confirmed
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0
download.file(url="https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv",
destfile = "data/time_series_covid19_deaths_global.csv")
time_series_deaths <- read_csv("data/time_series_covid19_deaths_global.csv") %>%
rename(Province_State = "Province/State", Country_Region = "Country/Region")
## Parsed with column specification:
## cols(
## .default = col_double(),
## `Province/State` = col_character(),
## `Country/Region` = col_character()
## )
## See spec(...) for full column specifications.
time_series_deaths_long <- time_series_deaths %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long),
names_to = "Date", values_to = "Deaths")
head(time_series_deaths_long)
## # A tibble: 6 x 6
## Province_State Country_Region Lat Long Date Deaths
## <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0
time_series_deaths_long_plot <- time_series_deaths_long %>%
group_by(Country_Region) %>%
summarise(Deaths = sum(Deaths)) %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_line() +
ggtitle("Confirmed COVID-19 deaths worldwide")
## `summarise()` ungrouping output (override with `.groups` argument)
time_series_confirmed_long <- time_series_confirmed_long %>%
unite(Key, Province_State, Country_Region, Date, sep = ".", remove = FALSE)
head(time_series_confirmed_long)
## # A tibble: 6 x 7
## Key Province_State Country_Region Lat Long Date Confirmed
## <chr> <chr> <chr> <dbl> <dbl> <chr> <dbl>
## 1 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/22/~ 0
## 2 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/23/~ 0
## 3 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/24/~ 0
## 4 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/25/~ 0
## 5 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/26/~ 0
## 6 NA.Afghanista~ <NA> Afghanistan 33.9 67.7 1/27/~ 0
time_series_deaths_long <- time_series_deaths_long %>%
unite(Key, Province_State, Country_Region, Date, sep = ".") %>%
select(Key, Deaths)
time_series_long_joined <- full_join(time_series_confirmed_long, time_series_deaths_long, by = c("Key")) %>%
select(-Key)
head(time_series_long_joined)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Confirmed Deaths
## <chr> <chr> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 1/22/20 0 0
## 2 <NA> Afghanistan 33.9 67.7 1/23/20 0 0
## 3 <NA> Afghanistan 33.9 67.7 1/24/20 0 0
## 4 <NA> Afghanistan 33.9 67.7 1/25/20 0 0
## 5 <NA> Afghanistan 33.9 67.7 1/26/20 0 0
## 6 <NA> Afghanistan 33.9 67.7 1/27/20 0 0
which(is.na(time_series_long_joined$Confirmed))
## integer(0)
which(is.na(time_series_long_joined$Deaths))
## integer(0)
time_series_joined_ex5 <- time_series_long_joined %>%
filter (Country_Region == "US") %>%
drop_na(Deaths, Confirmed) %>%
mutate(Deaths_confirmed = Deaths / Confirmed)
str(time_series_joined_ex5)
## tibble [251 x 8] (S3: tbl_df/tbl/data.frame)
## $ Province_State : chr [1:251] NA NA NA NA ...
## $ Country_Region : chr [1:251] "US" "US" "US" "US" ...
## $ Lat : num [1:251] 40 40 40 40 40 40 40 40 40 40 ...
## $ Long : num [1:251] -100 -100 -100 -100 -100 -100 -100 -100 -100 -100 ...
## $ Date : chr [1:251] "1/22/20" "1/23/20" "1/24/20" "1/25/20" ...
## $ Confirmed : num [1:251] 1 1 2 2 5 5 5 6 6 8 ...
## $ Deaths : num [1:251] 0 0 0 0 0 0 0 0 0 0 ...
## $ Deaths_confirmed: num [1:251] 0 0 0 0 0 0 0 0 0 0 ...
time_series_joined_ex5 %>%
group_by(Country_Region,Date) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = Deaths_confirmed))+
geom_point() +
geom_line() +
ggtitle("US COVID-19 deaths/confirmed cases per day")
## geom_path: Each group consists of only one observation. Do you need to
## adjust the group aesthetic?
library(lubridate)
## Warning: package 'lubridate' was built under R version 3.6.3
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
time_series_long_joined$Date <- mdy(time_series_long_joined$Date)
library(DT)
## Warning: package 'DT' was built under R version 3.6.3
time_series_long_joined %>%
group_by(Country_Region) %>%
summarize(Deaths = sum(Deaths, na.rm = TRUE)) %>%
slice_max(Deaths, n = 10) %>%
arrange(desc(Deaths))
## `summarise()` ungrouping output (override with `.groups` argument)
## # A tibble: 10 x 2
## Country_Region Deaths
## <chr> <dbl>
## 1 US 22505112
## 2 Brazil 11363329
## 3 United Kingdom 6408784
## 4 Italy 5941499
## 5 Mexico 5656827
## 6 India 5115949
## 7 France 4983267
## 8 Spain 4881010
## 9 Iran 2353899
## 10 Peru 2345552
time_series_long_joined %>%
filter(Country_Region %in% c("US", "Brazil", "United Kingdom", "Italy", "Mexico", "France", "Spain", "India", "Iran", "Peru")) %>%
ggplot(aes(x = Date, y = Deaths, color = Country_Region)) +
geom_point() +
geom_line() +
ggtitle("Top 10 Countries with COVID-19-related Deaths")
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Deaths"), sum) %>%
filter (Country_Region %in% c("US", "Brazil", "United Kingdom", "Italy", "Mexico", "France", "Spain", "India", "Iran", "Peru")) %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("COVID-19 Deaths") +
facet_wrap(~Country_Region, ncol=2, scales="free_y") +
theme_dark()
time_series_joined_ex5 %>%
group_by(Province_State,Date) %>%
summarise_at(c("Confirmed"), sum) %>%
ggplot(aes(x = Date, y = Confirmed)) +
geom_point() +
geom_line() +
ggtitle("Confirmed COVID-19 cases in the US") +
facet_wrap(~Province_State, ncol=25, scales="free_y")
## geom_path: Each group consists of only one observation. Do you need to
## adjust the group aesthetic?
time_series_joined_ex5 %>%
ggplot(aes(x = Date, y = Confirmed), size = 0.5) +
geom_point() +
geom_line() +
ggtitle("Confirmed COVID-19 cases in the US") +
facet_wrap(~Province_State, ncol=5, scales="free_y")
## geom_path: Each group consists of only one observation. Do you need to
## adjust the group aesthetic?
time_series_long_joined_counts <- time_series_long_joined %>%
pivot_longer(-c(Province_State, Country_Region, Lat, Long, Date),
names_to = "Report_Type", values_to = "Counts")
head(time_series_long_joined_counts)
## # A tibble: 6 x 7
## Province_State Country_Region Lat Long Date Report_Type Counts
## <chr> <chr> <dbl> <dbl> <date> <chr> <dbl>
## 1 <NA> Afghanistan 33.9 67.7 2020-01-22 Confirmed 0
## 2 <NA> Afghanistan 33.9 67.7 2020-01-22 Deaths 0
## 3 <NA> Afghanistan 33.9 67.7 2020-01-23 Confirmed 0
## 4 <NA> Afghanistan 33.9 67.7 2020-01-23 Deaths 0
## 5 <NA> Afghanistan 33.9 67.7 2020-01-24 Confirmed 0
## 6 <NA> Afghanistan 33.9 67.7 2020-01-24 Deaths 0
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = Deaths))+
geom_point() +
geom_line() +
ggtitle("US COVID-19 Deaths")
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("China","Japan", "Korea, South","Italy","Spain","US")) %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("COVID-19 Deaths") +
facet_wrap(~Country_Region, ncol=2, scales="free_y")
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("China","France","Italy","Korea, South","US")) %>%
ggplot(aes(x = Date, y = Deaths, color = Country_Region)) +
geom_point() +
geom_line() +
ggtitle("COVID-19 Deaths")
time_series_long_joined_counts %>%
group_by(Country_Region, Report_Type, Date) %>%
summarise(Counts = sum(Counts)) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = log2(Counts), fill = Report_Type, color = Report_Type)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Cases")
## `summarise()` regrouping output by 'Country_Region', 'Report_Type' (override with `.groups` argument)
pdf("file_name.pdf", width=6, height=3)
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US") %>%
ggplot (aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Deaths")
dev.off()
## png
## 2
ppi <- 300
png("time_series_ex5_1.png", width=6*ppi, height=6*ppi, res=ppi)
time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US") %>%
ggplot(aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Deaths")
dev.off()
## png
## 2
library(plotly)
## Warning: package 'plotly' was built under R version 3.6.3
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
US_deaths <- time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region == "US")
p <- ggplot(data = US_deaths, aes(x = Date, y = Deaths)) +
geom_point() +
geom_line() +
ggtitle("US COVID-19 Deaths")
ggplotly(p)
library(gganimate)
## Warning: package 'gganimate' was built under R version 3.6.3
## No renderer backend detected. gganimate will default to writing frames to separate files
## Consider installing:
## - the `gifski` package for gif output
## - the `av` package for video output
## and restarting the R session
library(transformr)
## Warning: package 'transformr' was built under R version 3.6.3
theme_set(theme_minimal())
data_time <- time_series_long_joined %>%
group_by(Country_Region,Date) %>%
summarise_at(c("Confirmed", "Deaths"), sum) %>%
filter (Country_Region %in% c("China","Korea, South","Japan","Italy","US"))
p <- ggplot(data_time, aes(x = Date, y = Confirmed, color = Country_Region)) +
geom_point() +
geom_line() +
ggtitle("Confirmed COVID-19 Cases") +
geom_point(aes(group = seq_along(Date))) +
transition_reveal(Date)
animate(p, end_pause = 15)
## Warning: No renderer available. Please install the gifski, av, or magick
## package to create animated output